An automotive radarsensor can be misaligned compared to the initial installation state due to various external shocks while driving, and it can cause deterioration of radar detection performance. To guarantee the sta...
详细信息
ISBN:
(纸本)9798350303872
An automotive radarsensor can be misaligned compared to the initial installation state due to various external shocks while driving, and it can cause deterioration of radar detection performance. To guarantee the stable detection performance of the radar, a method of estimating the deviation angle compared to the initial state is required. To directly check the radar misalignment, an inefficient bumper removal process is required, so a method of indirectly determining the mounting state of the radar is required. Therefore, in this paper, we propose a method for estimating the tilt angle of the radarsensor using deep neural networks (DNNs). First, radarsensordata are obtained at various radar tilt angles and measurement distances to identify the characteristics of received signals. Then, we extract range profiles from the received signals and design a DNN-based estimator using the profiles as input vectors. The proposed angle estimator consists of several DNNs in parallel, and the input vector passes through one of them according to the distance estimated from the range profile. Finally, the DNN determines the tilt angle for the input vector. In our datasets, the average classification accuracy of the proposed DNN-based classifier is over 98%.
In the radar-based air-writing, the hand movement may not be completely detected depending on the transmission cycle of the radar waveform, which potentially reduces the legibility of the air-writing results. Therefor...
详细信息
ISBN:
(纸本)9788831299091;9798350394436
In the radar-based air-writing, the hand movement may not be completely detected depending on the transmission cycle of the radar waveform, which potentially reduces the legibility of the air-writing results. Therefore, in this paper, we propose a method of interpolating the unmeasured portions of the air-writing using polynomial regression. First, using a radarsensor, we acquire range and angle detection results for hand motion over time. Then, the trajectory of the hand motion is expressed in two-dimensional distance coordinates using the range and angle information. Subsequently, the polynomial regression is used to derive the relationship between the observation time and the change of distance coordinates in each dimension. Next, we interpolate the unmeasured portions using the derived regression model and generate the interpolated air-writing results. Finally, to verify the performance of the proposed method, the recognition accuracy of non-interpolated and interpolated air-writing results is evaluated. In other words, we evaluate the recognition accuracy when the two results are input to a convolutional neural network trained with the modified national institute of standards and technologydatabase. The average recognition accuracy of interpolated air-writing results was 65.4%p higher than that of non-interpolated air-writing results.
sensors such as cameras, lidars, and radars are crucial to understanding driving situations in autonomous vehicles. These sensors are susceptible to external and internal abnormalities, potentially leading to severe t...
详细信息
ISBN:
(纸本)9798350382617
sensors such as cameras, lidars, and radars are crucial to understanding driving situations in autonomous vehicles. These sensors are susceptible to external and internal abnormalities, potentially leading to severe traffic accidents. A radarsensor is inevitably affected by the obstruction caused by small objects, which can cause the system to malfunction. This paper presents a deep learning approach for detecting anomalies in radardata. The accuracy of anomaly detection is improved by using radar-camera fusion. Our proposed model detects the data anomaly by calculating the deviation from the standard radar cross section (RCS) range. The result demonstrates that the model is capable of identifying the normal range of radar signal and anomaly signal under several different obtained features situations. It enables the detection of potential hazards and warns of dangers to drivers and higher-level control systems, creating a more resilient environment for ensuring autonomous driving safety.
This paper aims to explore the automotive safety research based on multi-sensor information fusion technology, which can integrate the information of multiple sensors to improve the accuracy and reliability to better ...
详细信息
Existing soil moisture sensing methods require either plugging probes into soil or burying sensor nodes or aluminum plate in soil. These methods either have mobility and maintenance limitations or have risks of batter...
详细信息
In the rapidly advancing field of autonomous driving technologies, the demand for more reliable and robust systems for sensing different parameters has witnessed a significant upsurge. Particularly, the reliability an...
详细信息
The fusion of millimeter-wave radar and optical camera is a challenge in the multi-sensordata fusion *** this paper a new space calibration algorithm is proposed to match the low-resolution radar point cloud informat...
详细信息
Human activity recognition (HAR) with radar-based technologies has become a popular research area in the past decade. However, the objective of these studies are often to classify human activity for anyone;thus, model...
详细信息
ISBN:
(纸本)9781510674158;9781510674141
Human activity recognition (HAR) with radar-based technologies has become a popular research area in the past decade. However, the objective of these studies are often to classify human activity for anyone;thus, models are trained using data spanning as broad a swath of people and mobility profiles as possible. In contrast, applications of HAR and gait analysis to remote health monitoring require characterization of the person-specific qualities of a person's activities and gait, which greatly depends on age, health and agility. In fact, the speed or agility with which a person moves can be an important health indicator. In this study, we propose a multi-input multi-task deep learning framework to simultaneously learn a person's activity and agility. In this initial study, we consider three different agility states: slow, nominal, and fast. It is shown that joint learning of agility and activity improves the classification accuracy for both activity and agility recognition tasks. To the best of our knowledge, this study is the first work considering both agility characterization and personalized activity recognition using RF sensing.
A smart excavation monitoring system based on multi-sensordata fusion is introduced in this work. This system includes an intelligent monitoring platform, safety factor evaluation algorithm, various types of excavati...
详细信息
In recent years, the number of people counting systems in deployment has been increasing significantly. People counting systems can be used to automate the data collection for advertisement, and revenue projections as...
详细信息
ISBN:
(纸本)9798350311143
In recent years, the number of people counting systems in deployment has been increasing significantly. People counting systems can be used to automate the data collection for advertisement, and revenue projections as well as reduce energy costs using adaptive HVAC operations. However, a naive implementation of people counting systems may result in revealing some unintended information about the users/customers and higher power consumption from operating the systems continuously. In this paper, we study a mmWave Multiple Input Multiple Output (MIMO) radarsensor system for detecting the number of people in a confined space with the aims of low power consumption and minimal leakage of user information. In particular, we showed that a 3D convolutional neural network can accurately determine up to 4 people in a typical size room using a surprisingly minimal number of mmWave signatures ( less than 10) as its inputs.
暂无评论